Laser & Optoelectronics Progress, Volume. 55, Issue 5, 051013(2018)
Key Frame Extraction Algorithm of Sign Language Based on Compressed Sensing and SURF Features
Figures & Tables(8)
Fig. 2. Key frame extraction algorithm diagram of sign language based on compressed sensing and SURF feature
Fig. 3. Partial test videos. (a) Laboratory environment; (b) different environment and light conditions
Fig. 4. Time sequence diagram of interframe similarity curve extreme point. (a) Extreme point; (b) key frame
Fig. 5. Output key frames of three algorithms. (a) Proposed algorithm; (b) non-specific dynamic sign language video key frame detection algorithm; (c) unsupervised clustering algorithm
Table 1. Subshot segmentation and key frame detection
View tableTable 1. Subshot segmentation and key frame detection
Video sample Number of subshots Average key frame number /part position Test1 27 6/[2, 12, 40, 86, 113, 149] Test2 27 6/[7, 26, 51, 76, 100, 132] Test3 24 7/[33, 49, 67, 101, 129, 140, 167] Test4 24 7/[37, 55, 85, 115, 134, 153, 178]
Table 2. Comparison of experimental data
View tableTable 2. Comparison of experimental data
Item Proposed algorithm Non-specific dynamic sign language video key frame detection algorithm Unsupervised clustering algorithm Average number of key frames 7.125 9.375 12.958 Key frame leak detection rate /% 0.75 1.75 3.25 Average running time /s 13.551 11.236 18.912 Stability of key frame detection /% 98.25 93.75 82.50
Tools
Get Citation
Copy Citation Text
Min Wang, Zeyang Li, Chun Wang, Xinyuan Shi. Key Frame Extraction Algorithm of Sign Language Based on Compressed Sensing and SURF Features[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051013
Paper Information
Category: Image processing
Received: Dec. 19, 2017
Accepted: --
Published Online: Sep. 11, 2018
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20